snapshot...

modules/deeplearning/espcn.py

@@ -59,12 +59,12 @@ data_idx, label_idx = 1, 1
 data_param = data_params[data_idx]
 label_param = label_params[label_idx]
 
-x_70 = np.arange(70)
-y_70 = np.arange(70)
-#x_70_2 = x_70[3:67:2]
-#y_70_2 = y_70[3:67:2]
-x_70_2 = x_70[2:69:2]
-y_70_2 = y_70[2:69:2]
+x_134 = np.arange(134)
+y_134 = np.arange(134)
+#x_134_2 = x_134[3:131:2]
+#y_134_2 = y_134[3:131:2]
+x_134_2 = x_134[2:133:2]
+y_134_2 = y_134[2:133:2]
 
 
 def build_residual_conv2d_block(conv, num_filters, block_name, activation=tf.nn.leaky_relu, padding='SAME'):
@@ -202,11 +202,11 @@ class ESPCN:
         label = data.copy()
 
         data = data[:, data_idx, :, :]
-        data = resample(x_70, y_70, data, x_70_2, y_70_2)
+        data = resample(x_134, y_134, data, x_134_2, y_134_2)
         data = np.expand_dims(data, axis=3)
 
         # label = label[:, label_idx, :, :]
-        label = label[:, label_idx, 3:67:2, 3:67:2]
+        label = label[:, label_idx, 3:131:2, 3:131:2]
         # label = label[:, label_idx, 3:67, 3:67]
         label = np.expand_dims(label, axis=3)
 
@@ -375,6 +375,7 @@ class ESPCN:
         print(conv.shape)
 
         #conv = tf.nn.depth_to_space(conv, factor)
+        conv = tf.keras.layers.Conv2DTranspose(num_filters * (factor ** 2), 3, padding='same')(conv)
         print(conv.shape)
 
         self.logits = tf.keras.layers.Conv2D(1, kernel_size=3, strides=1, padding=padding, name='regression')(conv)
@@ -732,7 +733,7 @@ class ESPCN:
 def prepare(param_idx=1, filename='/Users/tomrink/data_valid_40.npy'):
     nda = np.load(filename)
     #nda = nda[:, param_idx, :, :]
-    nda_lr = nda[:, param_idx, 2:69:2, 2:69:2]
+    nda_lr = nda[:, param_idx, x_134_2, y_134_2]
     # nda_lr = resample(x_70, y_70, nda, x_70_2, y_70_2)
     nda_lr = np.expand_dims(nda_lr, axis=3)
     return nda_lr